Nils Hammerla | Research Associate

Nils Hammerla

A common setting in Activity Recognition is that sensors, such as triaxial accelerometers, are worn on the body or embedded into objects of daily use. The recorded multi-variate sensor streams undergo analysis in order to infer the activities that were performed by the user. Simple yet effective methods, such as k-NN classification using statistical features, often suffice to obtain impressive recognition accuracies. Therefore information about what subjects are doing is readily available, rendering activity segmentation a straight-forward followup task. However, so far relatively little work was invested into a further, detailed analysis of these segmented activities, although extracting their characteristics, i.e. how well these activities were performed, would be beneficial to a variety of applications spanning many domains.
My main research goal is to develop novel methods for the assessment of this motor skill, particularly for applications in medicine. Here many degenerative conditions such as Parkinson’s Disease and Dementia have a significant impact on motor abilities, where motor assessment is crucial for early intervention and treatment.




Expressy: Using a Wrist-Worn Inertial Measurement Unit to Add Expressiveness to Touch-Based Interactions
Wilkinson G, Kharrufa A, Hook J, Pursglove B, Haeuser H, Hammerla N, Wood G, Hodges S, Olivier P, ACM Conference on Human Factors in Computing Systems 20162832-2844
A study of wrist-worn activity measurement as a potential real-world biomarker for late life depression
O&#39, Brien J, Gallagher P, Stow D, Hammerla N, Ploetz T, Firbank M, Ladha C, Ladha K, Jackson D, McNaney R, Ferrier N, Olivier P, 18th Annual Conference of the International Society for Bipolar Disorders & 8th Biennial Conference of the International Society for Affective Disorders146-146
Deep, Convolutional, and Recurrent Models for Human Activity Recognition using Wearables
Hammerla N, Halloran S, Ploetz T, Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence1533-1540
Body-Worn Sensors in Parkinson's Disease: Evaluating Their Acceptability to Patients
Fisher JM, Hammerla NY, Rochester L, Andras P, Walker RW, Telemedicine and e-Health63-69
Optimising sampling rates for accelerometer-based human activity recognition
Khan A, Hammerla N, Mellor S, Ploetz T, Pattern Recognition Letters33-40


How did I do? Automatic Skill Assessment from Accelerometer Data
Khan A, Berlin E, Mellor S, Thompson R, Hammerla N, McNaney R, Olivier P, Ploetz T, ACM GetMobile18-22
CueS: cueing for upper limb rehabilitation in stroke
Holden A, McNaney R, Balaam M, Thompson R, Hammerla N, Ploetz T, Jackson D, Price C, Brkic L, Olivier P, British HCI '15 2015 British HCI Conference18-25
Let’s (not) Stick Together: Pairwise Similarity Biases Cross-Validation in Activity Recognition
Hammerla N, Ploetz T, UbiComp '15 ACM International Joint Conference on Pervasive and Ubiquitous Computing1041-1051
PD Disease State Assessment in Naturalistic Environments using Deep Learning
Hammerla N, Fisher J, Andras P, Rochester L, Walker R, Ploetz T, Twenty-ninth AAAI Conference on Artificial Intelligence (AAAI-2015)
Diri - the Actuated Helium Balloon: A Study of Autonomous Behaviour in Interfaces
Nowacka D, Hammerla N, Elsden C, Ploetz T, Kirk D, UbiComp '15 ACM International Joint Conference on Pervasive and Ubiquitous Computing349-360


Automated Surgical OSATS Prediction from Videos
Sharma Y, Ploetz T, Hammerla N, Mellor S, Mcnaney R, Olivier P, Deshmukh S, Mccaskie A, Essa I, IEEE 11th International Symposium on Biomedical Imaging (ISBI)461-464
Video Based Assessment of OSATS Using Sequential Motion Textures
Sharma Y, Bettadapura V, Ploetz T, Hammerla N, Mellor S, McNaney R, Olivier P, Deshmukh S, McCaskie A, Essa I, Fifth Workshop on Modeling and Monitoring of Computer Assisted Interventions (M2CAI)
Using unlabeled data in a sparse-coding framework for human activity recognition
Bhattacharya S, Nurmi P, Hammerla N, Pl&#246, tz T, Pervasive and Mobile Computing242-262


On Preserving Statistical Characteristics of Accelerometry Data using their Empirical Cumulative Distribution
Hammerla N, Kirkham R, Andras P, Ploetz T, International Symposium on Wearable Computers (ISWC)65-68
Dog's Life: Wearable Activity Recognition for Dogs
Ladha C, Hammerla N, Hughes E, Olivier P, Ploetz T, ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp)415-418
ClimbAX: Skill Assessment for Climbing Enthusiasts
Ladha C, Hammerla N, Olivier P, Ploetz T, ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp)235-244
Automatic correction of annotation boundaries in activity datasets by class separation maximization
Kirkham R, Khan A, Bhattacharya S, Hammerla N, Mellor S, Roggen D, Ploetz T, ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp): HASCA Workshop


A statistical aimbot detection method for online FPS games
Yu SY, Hammerla N, Yan J, Andras P, International Joint Conference on Neural Networks (IJCNN)1-8
Aimbot Detection in Online FPS Games Using a Heuristic Method Based on Distribution Comparison Matrix
Yu SY, Hammerla N, Yan J, Andras P, NEURAL INFORMATION PROCESSING, ICONIP 2012, PT V654-661
Automatic assessment of problem behavior in individuals with developmental disabilities
Ploetz T, Hammerla NY, Rozga A, Reavis A, Call N, Abowd GD, Ubicomp 2012: Proceedings of the 2012 ACM Conference on Ubiquitous Computing391-400
Aimbot detection in online FPS games using a heuristic method based on distribution comparison matrix
Yu S-Y, Hammerla N, Yan J, Andras P, 19th International Conference on Neural Information Processing (ICONIP)654-661
The mobile fitness coach: Towards individualized skill assessment using personalized mobile devices
Kranz M, M&#246, ller A, Hammerla N, Diewald S, Pl&#246, tz T, Olivier P, Roalter L, Pervasive and Mobile Computing203-215
Automatic Synchronization of Wearable Sensors and Video-Cameras for Ground Truth Annotation – A Practical Approach
Ploetz T, Chen C, Hammerla N, Abowd G, 16th Annual International Symposium on Wearable Computing (ISWC)
GymSkill: A Personal Trainer for Physical Exercises
Moeller A, Roalter L, Diewald S, Kranz M, Hammerla N, Olivier P, Ploetz T, International Conference on Pervasive Computing and Communications (PerCom)213-220


GymSkill: Mobile Exercise Skill Assessment to Support Personal Health and Fitness
Moeller A, Scherr J, Roalter L, Diewald S, Kranz M, Hammerla N, Ploetz T, Olivier P, International Conference on Pervasive Computing (Pervasive)
Assessing Motor Performance with PCA
Hammerla N, Ploetz T, Andras P, Olivier P, International Workshop on Frontiers in Activity Recognition using Pervasive Sensing (in conjunction with Pervasive)
Cueing for drooling in Parkinson's disease
McNaney R, Lindsay S, Ladha K, Ladha C, Schofield G, Ploetz T, Hammerla N, Jackson D, Walker R, Miller N, Olivier P, 29th Annual CHI Conference on Human Factors in Computing Systems (CHI)619-622
Feature Learning for Activity Recognition in Ubiquitous Computing
Ploetz T, Hammerla N, Olivier P, International Joint Conference on Artificial Intelligence (IJCAI'11)1729-1734


Towards Feature Learning for HMM-based Offline Handwriting Recognition
Hammerla N, Ploetz T, Vajda S, Fink G, International Workshop on Frontiers of Arabic Handwriting Recognition

Associated Projects

  • Diri - the actuated helium balloon: a study of autonomous behaviour in interfaces
    As the sophistication of ubiquitous computing technologies increases, with advances in processing power and decreases in size users are being confronted with increasingly intelligent interfaces embedded in everyday devices. This raises an inter...
    August 30, 2011
  • Touchbugs: Actuated Tangibles on Multi-Touch Tables
    Touchbugs is an open source hardware and software framework for a novel actuated tangible technology. Touchbugs are small tangibles that use directed bristles and vibration motors for actuation (giving them the ability to move independently). Their inf...
    August 30, 2011
  • Activity Recognition to Improve Motor Performance in Parkinson's Disease
    Through sensors worn on the body or embedded into objects of daily use we can infer the activities performed by a subject. Extracting the characteristics of the data collected by these sensors, i.e. how these activities were performed, would be ben...
    August 30, 2011
    The aim of this project was to understand the changes in motor skill that take place during the early phases of learning a new fine motor skill task. For this project specifically, that motor skill was suturing, which we measured by attaching senso...
    August 30, 2011
  • Quantifying Human Motion for Medical Applications
    Often, high accuracy activity recognition can be performed using relatively simple methods, such as through the use of sensors like accelerometers and gyroscopes. This means that activity segmentation, meaning the extraction of continuous sequences...
    August 30, 2011
  • Cueing for Swallowing in Parkinson's
    This cueing device has been developed as a way to behaviourally manage drooling, which is commonly symptomatic of Parkinson’s Disease. The device was developed through a participatory design process, taking into account the needs of people with Parki...
    August 30, 2011
  • Cueing Technology for Parkinsons
    Approximately 70% of people with Parkinson’s Disease experience problems with swallowing. The resulting build-up of saliva can cause drooling, which is often a source of embarrassment and puts the person at risk of choking or pneumonia if the saliv...
    August 30, 2011
Copyright 2015 Open Lab